INDEX

Explanations

terms related to driving under the influence of alcohol or drugs

oai_token-act-pair · gpt-3.5-turbo

instances of being "under the influence" of substances

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ocre

-0.74

heed

-0.74

arcity

-0.72

oug

-0.68

chini

-0.66

ue

-0.65

helle

-0.65

anche

-0.63

apter

-0.63

weeney

-0.62

POSITIVE LOGITS

 Delicious

0.75

ħĭ

0.72

Roaming

0.71

lines

0.69

GUI

0.68

 Nightmares

0.68

ÙĴ

0.67

 provocation

0.66

ews

0.65

Frameworks

0.65

Activations Density 0.071%

terms related to driving under the influence of alcohol or drugs

instances of being "under the influence" of substances

No Comments

No Known Activations